{"total":50,"rows":[{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2102.07188","title":"Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces","created":"2021-02-14","cited_by_count":53,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2111.13755","title":"A survey on multi-objective hyperparameter optimization algorithms for Machine Learning","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2203.02128","title":"Distributionally Robust Bayesian Optimization with $\\varphi$-divergences","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2207.11120","title":"On Controller Tuning with Time-Varying Bayesian Optimization","created":"2022-07-22","cited_by_count":13,"area":null},{"id":"2202.03259","title":"Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration","created":"2022-02-07","cited_by_count":11,"area":null},{"id":"2402.01632","title":"Time-Varying Gaussian Process Bandits with Unknown Prior","created":"2024-02-02","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2304.02396","title":"AutoRL Hyperparameter Landscapes","created":"2023-04-05","cited_by_count":8,"area":null},{"id":"2201.11182","title":"Hyperparameter Tuning for Deep Reinforcement Learning Applications","created":"2022-01-26","cited_by_count":7,"area":null},{"id":"2208.10790","title":"Event-Triggered Time-Varying Bayesian Optimization","created":"2022-08-23","cited_by_count":7,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2112.01853","title":"Episodic Policy Gradient Training","created":"2021-12-03","cited_by_count":5,"area":null},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2212.10876","title":"Hyperparameters in Contextual RL are Highly Situational","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2306.01436","title":"Multi-Objective Population Based Training","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2104.04547","title":"High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Models","created":"2021-04-09","cited_by_count":3,"area":null},{"id":"2303.03394","title":"Agent-based Collaborative Random Search for Hyper-parameter Tuning and Global Function Optimization","created":"2023-03-03","cited_by_count":3,"area":null},{"id":"2311.15162","title":"Domain Knowledge Injection in Bayesian Search for New Materials","created":"2023-11-26","cited_by_count":3,"area":null},{"id":"2110.12087","title":"Gaussian Process Sampling and Optimization with Approximate Upper and Lower Bounds","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2111.15317","title":"AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2205.05272","title":"Hierarchical Collaborative Hyper-parameter Tuning","created":"2022-05-11","cited_by_count":2,"area":null},{"id":"2306.06844","title":"Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2503.00509","title":"Functional multi-armed bandit and the best function identification problems","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2308.08634","title":"FedPop: Federated Population-based Hyperparameter Tuning","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2501.15273","title":"Into the Void: Mapping the Unseen Gaps in High Dimensional Data","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2109.14925","title":"Genealogical Population-Based Training for Hyperparameter Optimization","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2301.06133","title":"Improving Reliability of Fine-tuning with Block-wise Optimisation","created":"2023-01-15","cited_by_count":0,"area":null},{"id":"2309.06604","title":"Hybrid Algorithm Selection and Hyperparameter Tuning on Distributed Machine Learning Resources: A Hierarchical Agent-based Approach","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2311.16781","title":"Generation of Games for Opponent Model Differentiation","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2405.09584","title":"Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2504.03926","title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2505.06630","title":"Dynamic Domain Information Modulation Algorithm for Multi-domain Sentiment Analysis","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2511.09190","title":"Iterated Population Based Training with Task-Agnostic Restarts","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2610.02828","title":"FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}